large

A Large Short-video Recommendation Dataset with Raw Text/Audio/Image/Videos (Talk Invited by DeepMind).

A pair of tiny foundational models trained in Brazilian Portuguese.🦙🦙

This is the official code for the paper "Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable".

Create a ChatGPT for uploaded pdf using Langchain

[ACL 2026 Oral] Official implementation of LaMI: Augmenting Large Language Models via Late Multi-Image Fusion

SiLLM is a Simultaneous Machine Translation (SiMT) Framework. It utilizes a Large Language model as the translation model and employs a traditional SiMT model for policy-decision to achieve SiMT through collaboration.

Free offline app to compress large video, images, audio & PDF — target exact MB/KB sizes and useful for all and also content creators for big files and video. And its completely free.

This project combines two functionalities: a Code Interpreter using LLM Agent Orchestration and Tool Utilization, and a ReAct LangChain Agent example.ReAct agent using LangChain, integrated with a custom tool to calculate the length of a given text. It serves as a foundational example for building more complex, tool-augmented LLM applications.

An alternative to libraries like Pinecone, which are notoriously expensive, so that you can store information for LLM queries in your local machine.

Comprehensive Evaluation On Answer Calibration For Multi-Step Reasoning

General purpose virtual assistant with GUI and LLMs.

inference-hive is a toolkit to run distributed LLM inference on SLURM clusters. Configure a few cluster, inference server and data settings, and scale your inference workload across thousands of GPUs.

🏆[ICML 2026 Spotlight] Official implementation of "DecodeShare: Tracing the Shared Subspace of LLM Decode-Time Decisions"

Automate Steam balance buying with AetherSwap: low-price tracking, cross-region purchase, market analysis, and full visual control

A hybrid stellar classifier that combines deterministic astrophysical rules (Hard Computing) with a fine-tuned LLM (AstroSage-8B) to assign MK spectral types and generate natural-language stellar descriptions from Gaia DR3 data.

AI-powered customer support assistant designed to handle food delivery complaints efficiently. Built using LangChain, RAG (Retrieval-Augmented Generation), PostgreSQL, and email automation, the chatbot provides empathetic, context-aware responses to customer queries regarding order status, payment issues, and refunds.

A template for large Flask apps, so you won't need to create the structure from scratch every time you start coding

A Python-based AI tool was developed to enhance the screening phase of systematic literature reviews by assigning semantic relevance scores (1–7) to studies using large language models (LLMs). Tested with ChatGPT, Gemini, and DeepSeek, the system’s outputs were compared to human evaluations from doctoral students and academics on 10 education-relat

An AI-powered web app to summarize and chat with any YouTube video using a modular LLM pipeline.